Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A systematic trust management system for RPL based IoT networks using machine learning.

Himani Tyagi1, Rajendra Kumar2, Santosh Kr Pandey3

  • 1Jamia Millia Islamia University, New Delhi, India. gaura.15.03.2021@gmail.com.

Scientific Reports
|July 7, 2026
PubMed
Summary

Related Concept Videos

Distribution Reliability and Automation01:25

Distribution Reliability and Automation

Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Genetic analysis of the SH gene of mumps virus genotype C in Kerala during 2024-25.

Virus genes·2026
Same author

Virtual reality and cheminformatics-driven discovery of a potential broad-spectrum natural antagonist against flaviviral methyltransferases and its cytotoxicity evaluation.

Journal of computer-aided molecular design·2025
Same author

Genome-wide association studies identified novel SNPs associated with efficient biological nitrogen fixation in chickpea (<i>Cicer arietinum</i> L.).

Frontiers in plant science·2025
Same author

Androgen Receptor Drives Polyamine Synthesis, Creating a Vulnerability for Prostate Cancer.

Cancer research·2025
Same author

Functional Outcomes of Intra-articular Distal Radius Fractures: Single-Incision Three-Column Fixation Using Volar Locking Plate and K-Wire Stabilization.

Cureus·2025
Same author

Symbiotic nitrogen fixation for sustainable chickpea yield and prospects for genome editing in changing climatic situations.

Frontiers in plant science·2025

This study introduces a novel Trust Management System (TMS) to secure Internet of Things (IoT) networks against attacks. The AI-driven system effectively predicts node trustworthiness, enhancing overall network security and reliability.

Area of Science:

  • Cybersecurity
  • Artificial Intelligence
  • Internet of Things (IoT)

Background:

  • Growing security risks in evolving Internet of Things (IoT) networks.
  • Existing security gaps include Blackhole, Decreased Rank, Version Number, and Flooding attacks, compromising node trustworthiness.
  • The need for robust Trust Management Systems (TMS) for secure routing and attack detection in IoT.

Purpose of the Study:

  • To propose a lightweight, reliable, and dynamic Trust Management System (TMS) to enhance IoT network security.
  • To address challenges in AI-driven IoT security, including data availability and trust uncertainty.
  • To develop a system capable of real-time trustworthiness prediction and attack detection.

Main Methods:

  • Proposed a novel TMS utilizing three trust indicators: network flows, recommendations, and social behavior.
Keywords:
ClusteringDetectionKELM (Kernel Extreme Learning Machine)Machine learningManagement systemRouting attacksTrust

Related Experiment Videos

  • Aggregated trust indicators using a modified Beta Distribution function to create trust labels for datasets.
  • Designed a lightweight Kernel Extreme Learning Machine (KELM) based predictor and a dynamic threshold evaluation module.

    • Main Results:

    • The proposed TMS achieved high performance in binary and multiclassification tasks.
    • Demonstrated superior performance compared to existing state-of-the-art TMS solutions.
    • Achieved 99.95% accuracy, 99.9% precision, 99.96% recall, with a 0.05% misclassification rate.

    Conclusions:

    • The developed lightweight and dynamic TMS significantly enhances IoT network security.
    • The novel approach effectively addresses trust-based attacks like Blackhole, Decreased Rank, Version Number, and Flooding.
    • The system offers accurate and reliable trustworthiness predictions, improving overall IoT security.